def scanSFS():
scores = rutl.loadScores()
field = comale;
df = sort(utl.scanGenome(scores.abs(), {field: lambda x: x.abs().mean(), 'Num. of SNPs': lambda x: x.size}))[
[field, 'Num. of SNPs']]
plotOne(df, df[df[field] > df[field].quantile(0.99)], fname='all')
nu0 = rutl.getNut(0)
nut = rutl.getNut(59)
reload(rutl)
# n= int(pd.read_pickle(utl.outpath + 'real/CD.F59.df').loc[:,pd.IndexSlice[:,0,'D']].mean().mean())
n = 100
SFSelect = lambda x: est.Estimate.getEstimate(x=x, method='SFSelect', n=n)
sf0 = scanOne(nu0, SFSelect, 'SFSelect.Base', 'SFSelect.Base');
SFSelect = lambda x: est.Estimate.getEstimate(x=x, method='SFSelect', n=n)
sft = scanOne(nut, SFSelect, 'SFSelect.Final', 'SFSelect.Final')
sfr = pd.concat(
[(sft.iloc[:, 0] - sf0.iloc[:, 0]).rename('SFS(59)-SFS(0)'), sf0.iloc[:, 0], sft.iloc[:, 0], df.iloc[:, 0]],
axis=1)
outlier = sfr[sfr.iloc[:, 0] > sfr.iloc[:, 0].quantile(0.99)]
sfr.loc[(sfr.iloc[:, 0] < 0).values, sfr.columns[0]] = None
fig = plt.figure(figsize=(7, 4.5), dpi=300);
pplt.Manhattan(data=sfr, Outliers=outlier, fig=fig, markerSize=2, ticksize=8, sortedAlready=True)
[pplt.setSize(ax, 5) for ax in fig.get_axes()]
plt.savefig(utl.paperPath + 'new/{}.pdf'.format('sfs-clear'))
def saveTopKSNPs():
scores = rutl.loadScores()
ann = loadANN()["Annotation Annotation_Impact Gene_Name Gene_ID".split()]
scores = pd.concat([scores, rutl.loadSNPIDs()], axis=1).set_index('ID', append=True)[0].rename('Hstatistic')
top = scores[scores > scores.quantile(0.9999)].reset_index('ID').join(rutl.getNut(0), how='inner')
top = top.join(ann).drop_duplicates().sort_values('Hstatistic', ascending=False)
top = top[top['Annotation_Impact'] != 'LOW']
top.to_csv(utl.outpath + 'real/top_1e-4_quantile_SNPs.csv')
def scanSFSSNPbased():
scores = rutl.loadScores(skipHetChroms=True)
# field = comale;
# df = sort(utl.scanGenome(scores.abs(), {field: lambda x: x.abs().mean(), 'Num. of SNPs': lambda x: x.size}))[
# [field, 'Num. of SNPs']]
# plotOne(df, df[df[field] > df[field].quantile(0.99)], fname='all')
reload(rutl)
reload(pplt)
reload(utl)
# SFSelect = lambda x: est.Estimate.getEstimate(x=x, method='SFSelect', n=100)
# sfs0 = utl.scanGenomeSNP(rutl.getNut(0, skipHetChroms=True), SFSelect)
# sfst = utl.scanGenomeSNP(rutl.getNut(59, skipHetChroms=True), SFSelect).rename(59); sfs=(sfst-sfs0); sfs[sfs<0]=None
g = ga.loadGeneCoordinates().set_index('name')
genes = g.loc[['Ace', 'Cyp6g1', 'CHKov1']].reset_index().set_index('CHROM')
shade = scores.sort_values().reset_index().iloc[-2:].rename(columns={'POS': 'start'});
shade['end'] = shade.start + 100
cand = pd.concat([scores, scores.rank(ascending=False).rename('rank'), rutl.getNut(0, skipHetChroms=True)],
axis=1).sort_values('rank')
chroms = ['2L', '2R', '3L', '3R']
reload(utl)
# reload(pplt);pplt.Genome(sfs.loc[chroms],genes=genes);plt.tight_layout(pad=0.1)
df = pd.concat(
[utl.scanGenomeSNP(scores.abs(), lambda x: x.mean(), winSize=200, step=100, skipFromFirst=900).rename(200),
utl.scanGenomeSNP(scores.abs(), lambda x: x.mean(), winSize=500, step=100, skipFromFirst=750).rename(500),
utl.scanGenomeSNP(scores.abs(), lambda x: x.mean(), winSize=1000, step=100, skipFromFirst=500).rename(
1000)], axis=1)
df['comb'] = df[200] * df[500] * df[1000]
fig = plt.figure(figsize=(7, 4.5), dpi=300);
pplt.Manhattan(data=sort(df.rename(columns={'comb': '200*500*1000'})), fig=fig, markerSize=2, ticksize=8,
sortedAlready=True);
[pplt.setSize(ax, 5) for ax in fig.get_axes()];
plt.gcf().subplots_adjust(bottom=0.15);
plt.savefig(utl.paperPath + 'new/{}.pdf'.format('SNPbased'))
pplt.Genome(df.comb);
plt.tight_layout(pad=0.1)
# analyzie()
# scanSFS()
# outlier()
# scanSFSSNPbased()
a = df.comb
o = localOutliers(a, q=0.9);
fig = plt.figure(figsize=(7, 1.5), dpi=300);
pplt.Manhattan(data=a, Outliers=pd.DataFrame(o), fig=fig, markerSize=2, ticksize=8, sortedAlready=True);
[pplt.setSize(ax, 5) for ax in fig.get_axes()];
plt.gcf().subplots_adjust(bottom=0.15);
plt.savefig(utl.paperPath + 'new/{}.pdf'.format('SNPbased.candidates'))
Scores = pd.concat([scores.rename('scores').abs(), scores.groupby(level=0).apply(
lambda x: pd.Series(range(x.size), index=x.loc[x.name].index)).rename('i')], axis=1)
cutoff = FDR(o, Scores);
a = pd.concat([df, cutoff[cutoff.sum(1) > 0]], axis=1).dropna();
for fdr in [0.95, 0.99, 0.999]:
o = a[a.comb > a[fdr]]
fig = plt.figure(figsize=(7, 1.5), dpi=300);
pplt.Manhattan(data=df.comb, Outliers=pd.DataFrame(o), fig=fig, markerSize=2, ticksize=8, sortedAlready=True);
[pplt.setSize(ax, 5) for ax in fig.get_axes()];
plt.gcf().subplots_adjust(bottom=0.15);
plt.savefig(utl.paperPath + 'new/{}.pdf'.format('SNPbased.fdr{}'.format(fdr)))
